GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
ECCV2026
https://t.co/DmVZ59AmAs
Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial structure and appearance. Unlike diffusion-based methods that refine scenes holistically, our formulation constructs scenes step-by-step, naturally supporting completion, outpainting, controllable sampling via temperature, and flexible generation horizons. This formulation leverages the compositional inductive biases and scalability of autoregressive modeling while operating on explicit representations compatible with modern neural rendering pipelines, positioning autoregressive transformers as a complementary paradigm for controllable and context-aware 3D generation.
New release of #PyViz3D 🚀-- directly render 3D point clouds, graphs and more in @Blender 🤹🏻♂️
👩💻Code+examples: https://t.co/Aoq9wih2Rf
🛠️Install: pip3 install pyviz3d
Good time to create beautiful figures for your @eccvconf supplementary or @CVPR workshop submissions✍️⏰
🎉 V1.0.0 officially released!
* New splatfacto model, nerfstudio's implementation of Gaussian splatting
* Complete rewrite of the viewer, now built entirely on viser
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
paper page: https://t.co/hcrwbkSP1Q
introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications.
🌪️ Despite the ongoing super Typhoon Saola in Hong Kong, I'm excited to introduce PointLLM! 🌈🔍 It's a multi-modal large language model that understands point clouds. 1/4🧵
🔗 Demo: http://101.230.144.196
📄 Paper: https://t.co/nSbUkqUaV4
💻 Code: https://t.co/SX7r3ClzX3